RAFNet: RGB-D attention feature fusion network for indoor semantic segmentation

Semantic segmentation based on the complementary information from RGB and depth images has recently gained great popularity, but due to the difference between RGB and depth maps, how to effectively use RGB-D information is still a problem. In this paper, we propose a novel RGB-D semantic segmentation network named RAFNet, which can selectively gather features from the RGB and depth information. Specifically, we construct an architecture with three parallel branches and propose several complementary attention modules. This structure enables a fusion branch and we add the Bi-directional Multi-step Propagation (BMP) strategy to it, which can not only retain the feature streams of the original RGB and depth branches but also fully utilize the feature flow of the fusion branch. There are three kinds of complementary attention modules that we have constructed. The RGB-D fusion module can effectively extract important features from the RGB and depth branch streams. The refinement module can reduce the loss of semantic information and the context aggregation module can help propagate and integrate information better. We train and evaluate our model on NYUDv2 and SUN-RGBD datasets, and prove that our model achieves state-of-the-art performances.     

Supporting inconsistent rules in database systems

When a set of rules generates (conflicting) values for a virtual attribute of some tuple, the system must resolve the inconsistency and decide on a unique value that is assigned to that attribute. In most current systems, the conflict is resolved based on criteria that choose one of the rules in the conflicting set and use the value that it generated. There are several applications, however, where inconsistencies of the above form arise, whose semantics demand a different form of resolution. We propose a general framework for the study of the conflict resolution problem, and suggest a variety of resolution criteria, which collectively subsume all previously known solutions. With several new criteria being introduced, the semantics of several applications are captured more accurately than in the past. We discuss how conflict resolution criteria can be specified at the schema or the rule-module level. Finally, we suggest some implementation techniques based on rule indexing, which allow conflicts to be resolved efficiently at compile time, so that at run time only a single rule is processed.An earlier version of this work appeared under the title Conflict Resolution of Rules Assigning Values to Virtual Attributes inProceedings of the 1989 ACM-Sigmod Conference, Portland, OR, June 1989, pp. 205–214.Partially supported by the National Science Foundation under Grant IRI-9157368 (PYI Award) and by grants from DEC, HP, and AT&T.Partially supported by the National Science Foundation under Grant IRI-9057573 (PYI Award), IBM, DEC, and the University of Maryland Institute for Advanced Computer Studies (UMIACS).     

基于描述逻辑的OntoUML模型的形式化表示

将形式本体理论应用于UML语言的改进是UML的形式化研究的主要方法之一,其中On-toUML是一个概念上完整、语义上清晰和更具本体意义的UML版本。虽然OntoUML基于本体对UML进行了扩充,提供了更为丰富,更能表达现实世界语义的建模原语,但其表达方式不利于在信息系统的设计与开发中应用。本文基于描述逻辑对OntoUML中的关键建模原语及其关系给出了SHIQ形式化表示方法,并进行了实例研究。该方法表达精练、语义清晰,不仅能够表达逻辑清晰的模型,而且保证模型能够正确反映领域事实。这种形式化方法为信息系统概念建模方法提供了理论和应用支撑,在一定程度上推动了OntoUML更为广泛的应用。     

图像中的文本定位技术研究综述

介绍了图像中文本定位技术的研究现状,依据定位所利用的特征进行分类,分析了其中几种典型算法,并对文本定位算法的性能评价标准进行了深入讨论。     

一种新颖的低层视觉特征到高层语义的映射方法*

通过在低层视觉特征上提取图像的局部颜色和纹理特征,再利用模糊神经网络建立低层视觉特征和高层语义特征之间的映射,实现了图像属性信息的有效传递和可靠检索.最后,为了提高检索效率,把相关反馈引进到图像检索系统中.实验证明,该方法取得了较好的检索查全率和准确率.     

基于图的语义网络构造算法研究

在自然语言处理的基础上,将中医领域本体与图的基本性质相结合,提出了构造中医诊疗知识语义网络算法。给出了图的基本性质、语义网络的图定义,并为知识的网络表示建立了相应的数据结构。将算法用于中医领域语义网络和语义场构建。试验结果表明,该算法具有较好的实用性。提出的基于图的语义网络构造算法,对于文本挖掘、知识获取技术研究有重要意义,也是中医专家知识获取的有效方法。     

Semantic weak signal tracing

The weak signal concept according to Ansoff has the aim to advance strategic early warning. It enables to predict the appearance of events in advance that are relevant for an organization. An example is to predict the appearance of a new and relevant technology for a research organization. Existing approaches detect weak signals based on an environmental scanning procedure that considers textual information from the internet. This is because about 80% of all data in the internet are textual information. The texts are processed by a specific clustering approach where clusters that represent weak signals are identified. In contrast to these related approaches, we propose a new methodology that investigates a sequence of clusters measured at successive points in time. This enables to trace the development of weak signals over time and thus, it enables to identify relevant weak signal developments for organization’s decision making in strategic early warning environment.     

Text classification using genetic algorithm oriented latent semantic features

In this paper, genetic algorithm oriented latent semantic features (GALSF) are proposed to obtain better representation of documents in text classification. The proposed approach consists of feature selection and feature transformation stages. The first stage is carried out using the state-of-the-art filter-based methods. The second stage employs latent semantic indexing (LSI) empowered by genetic algorithm such that a better projection is attained using appropriate singular vectors, which are not limited to the ones corresponding to the largest singular values, unlike standard LSI approach. In this way, the singular vectors with small singular values may also be used for projection whereas the vectors with large singular values may be eliminated as well to obtain better discrimination. Experimental results demonstrate that GALSF outperforms both LSI and filter-based feature selection methods on benchmark datasets for various feature dimensions.     

基于分布的中文词表示研究

针对基于分布的中文词表示构造过程中的参数选择问题进行了系统性的研究。选择了六种参数进行对比实验,在中文语义相似度任务上对不同参数设置下得到的中文词表示的质量进行了评估。实验结果表明,通过选择合适的参数,基于分布的词表示在中文语义相似度任务上能够得到较高的性能,而且,这种高维的词分布表示的质量甚至优于目前流行的基于神经网络（Skip-gram）或矩阵分解（GloVe）得到的低维的词表示。     

基于随机游走模型的维基百科语义关系研究

运用随机游走模型提出了一种基于维基百科的语义相关度的计算方法。维基百科中包含了丰富的链接结构,这些链接结构一定程度上能够反应词条之间概念上的相关性,以内容链接和外部链接关系来计算基于维基百科的语义相关度,并在WS-353数据集上进行了实验,取得了较好的准确性。